ktx-context-layer-data-agents

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests data from external, potentially untrusted sources which could contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: The skill ingests data from contextSources (specifically dbt manifest files and Notion databases) as well as SQL data warehouses (SKILL.md).
  • Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat ingested data as untrusted or to ignore embedded natural language commands within those sources.
  • Capability inventory: The skill provides an MCP server, search tools for a semantic layer, and the ability to execute SQL queries through the ktx client (SKILL.md).
  • Sanitization: No sanitization or validation logic is described for the content retrieved from external sources before it is processed by the LLM.
  • [EXTERNAL_DOWNLOADS]: The skill installs the @kaelio/ktx package from the NPM registry and utilizes npx for execution.
  • The skill recommends the global installation of @kaelio/ktx via npm or execution via npx (SKILL.md).
  • This package is a vendor-provided resource associated with the skill author.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 01:04 AM
Security Audit — agent-trust-hub — ktx-context-layer-data-agents